adversarial-review skillA

adversarial-review is agent-read markdown (skill) from sathiaai/adversarial-review: Independent adversarial review and deterministic release gating for code changes, using a multi-model reviewer panel over OpenRouter (or any OpenAI-compatible router, or an MCP transport like Composio). Use whenever the user asks for an adversarial review, red-team review, multi-model review, independent review, release gate, pre-merge or pre-release verification, "is this safe to ship/merge/deploy", or asks to verify a change with models other than the one that wrote it. Also use when the user .

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Adversarial Review

You are gating production software. The work is not complete until it passes deterministic
verification AND independent adversarial review, and the final verdict is **computed by
`scripts/aggregate.py` from recorded artifacts — never by you**. You ran or advised this
change, which makes you a conflicted party: your job here is to operate the pipeline
faithfully, not to judge the outcome.

Why this structure exists: a model that helped build a change has every incentive (and
blind spot) to see it as correct. So correctness claims must come from (a) deterministic
tools with exit codes, and (b) reviewer models from providers that did NOT participate in
development — and the PASS/FAIL/BLOCKED decision is computed from those artifacts by a
script you cannot argue with.

## Non-negotiable rules

- A model or provider family involved in planning, coding, debugging, or advising this
  change never reviews it independently. That includes you.
- Passing AI review never overrides a deterministic failure.
- Never weaken tests, thresholds, or scanner rules to obtain a pass.
- Never suppress a finding without a narrow, documented, expiring justification
…

Read the whole file at its exact version.

How to install

Latest version
mdr add sathiaai/adversarial-review/adversarial-review@git:20260919.6aa7a7e
Exact content
mdr add sathiaai/adversarial-review/adversarial-review@sha256:22012eb447253666

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_neogasxzubcmydva.svg)](https://markdownregistry.com/a/art_neogasxzubcmydva)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260919.6aa7a7e latest2026-09-19 6aa7a7e 18,448 BA view · diff
git:20260918.5f0cd2e2026-09-18 5f0cd2e 18,331 BA view · diff
git:20260812.8c921172026-08-12 8c92117 15,961 BA view · diff
git:20260812.9a9d6a12026-08-12 9a9d6a1 15,611 BA view · diff
git:20260808.48f77e12026-08-08 48f77e1 14,914 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (18448 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

sathiaai/adversarial-review · 3 stars · license MIT · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_neogasxzubcmydva
GET https://markdownregistry.com/api/v1/resolve?ref=sathiaai/adversarial-review/adversarial-review
GET https://markdownregistry.com/api/v1/blob/22012eb447253666d14d506e30a95ac1573e6f0a2c78f47d9642f0aa864eb136

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from sathiaai/adversarial-review

AGENTS.md agents
sathiaai/adversarial-review · AGENTS.md
git:20260808.48f77e1 · audit A · 3 stars
llms.txt llmstxt
sathiaai/adversarial-review · llms.txt
git:20260808.c6c16d5 · audit A · 3 stars
intended-vs-implemented skill
sathiaai/adversarial-review · skills/intended-vs-implemented/SKILL.md · Verify what the code actually does against what the docs, roadmap, or handoff claim it does — the code is the source of…
git:20260910.c480f23 · audit A · 3 stars
pr-text-check skill
sathiaai/adversarial-review · skills/pr-text-check/SKILL.md · Make the PR description, commit messages, and CHANGELOG match what actually changed — no drift, honest status, docs in…
git:20260910.c480f23 · audit A · 3 stars
shipping-artifacts skill
sathiaai/adversarial-review · skills/shipping-artifacts/SKILL.md · Every claim ships with the artifact that proves it — test output, a run dir, an attestation, a review verdict. Use when…
git:20260910.c480f23 · audit A · 3 stars
spec-driven-development skill
sathiaai/adversarial-review · skills/spec-driven-development/SKILL.md · Write the spec before the code, make the spec the contract, and loop until the implementation is verified against it…
git:20260910.c480f23 · audit A · 3 stars

Every file in sathiaai/adversarial-review

Other files named adversarial-review

adversarial-review skill
basicmachines-co/basic-memory · .agents/skills/adversarial-review/SKILL.md · Cross-vendor adversarial code review of the current branch. Two different model families (Claude + Codex/GPT) review…
git:20260530.4ea03d2 · audit A · 4,028 stars
adversarial-review skill
a5c-ai/babysitter · library/methodologies/metaswarm/skills/adversarial-review/SKILL.md · Fresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via…
git:20260601.da7723a · audit A · 1,809 stars
adversarial-review skill
event4u-app/agent-config · src/skills/adversarial-review/SKILL.md · Adversarial critique — devil's advocate, stress-test, honest teardown ('poke holes', 'be brutal', 'was hältst du…
git:20260906.720eb73 · audit A · 10 stars
adversarial-review skill
ucsandman/claude-skills · adversarial-review/SKILL.md · Multi-agent adversarial code review - parallel finders, verified by a skeptic. Use for "adversarial review" or "did the…
git:20260904.14d2e37 · audit A · 5 stars
adversarial-review skill
s977043/river-review · skills/agent-skills/adversarial-review/SKILL.md · 敵対的分析手法を統合したレビューの entry skill。認知バイアス対策の3手法 (Pre-mortem / War Game / Logic Torturing)と、宣言・主張と実態の乖離を突く claim-vs-actual…
v0.1.0 · audit A · 3 stars
adversarial-review skill
okisdev/claude-code-fusion · plugins/codex/skills/adversarial-review/SKILL.md · Runs a read only Codex review that challenges implementation and design decisions. Use when preparing to merge a…
git:20260722.ded22f9 · audit A · 3 stars

Browse by kind, by grade A, or by owner.